把物体P进照片，这次连光影和角度都一起改了
现在的AI把东西P进照片，基本是贴图：物体是贴上去的，光影、透视、角度都不对，一眼假。这篇让AI同时改物体和它周围的环境——物体插进去，它投下的影子、周围被它挡住的背景、光照方向，全都跟着变，而且你换一个视角看，物体和场景还是对得上的。研究者用Blender渲染出大量「同一场景、有/无物体」的成对图片来训练，让AI学会的不只是物体长什么样，还有它和场景怎么互相影响。用户测试里，大家觉得它放的位置、光影融合、透视和姿态都比以前可信。它不是你明天就能用的工具，但这是「P图不穿帮」从贴图走向物理模拟的一步。
📄 原文摘要(英文)
We present PhysInsert, a framework for physically plausible reference-based object insertion that jointly adapts objects and their surrounding scenes. Existing methods often rely on masked inputs, generation-based pairs, or training pairs with limited viewpoint variation, leaving pose and illumination adaptation and bidirectional object-scene interactions insufficiently constrained. We construct the Insert World dataset with strictly aligned Blender-rendered counterfactual pairs and object references across viewpoints and lighting conditions. Building on these data, Geometry-Guided Adaptation couples a VGGT geometry stream with image and text streams under target-scene feature supervision to guide spatially consistent insertion. Complementary 2D Object-Scene Spatial Supervision jointly supervises object occupancy and environmental changes while grounding spatial instructions in object regions through image-text attention. We introduce PhysInsert-Bench with dedicated cross-environment and cross-view cases requiring illumination and pose adaptation beyond appearance copying. Experiments on PhysInsert-Bench and DreamBooth demonstrate improved image fidelity; a user study further shows more accurate placement and improved lighting integration, perspective, and pose plausibility.